Automatic Parking Method and Apparatus

This is a continuation of International Patent Application No. PCT/CN2022/133484 filed on Nov. 22, 2022, the disclosure of which is hereby incorporated by reference in its entirety.

This disclosure relates to the field of autonomous driving technologies, and in particular, to an automatic parking method and apparatus.

With development of intelligent driving technologies, to meet people's pursuit of convenient and safe parking experience, an automatic parking function is increasingly widely applied. The automatic parking function can be applied to a cruise phase and a parking phase. In the cruise phase, the automatic parking function is mainly used to detect a parking space, and in the parking phase, the automatic parking function is mainly used to park a vehicle in a detected parking space.

However, when the current automatic parking function detects a parking space, obstacle information may be recognized as parking space information, that is, an obstacle that is not a parking space is recognized as a parking space. Subsequently, when a vehicle is parked in the detected inaccurate parking space, a risk of colliding with various obstacles such as another vehicle may occur.

Therefore, how to improve accuracy of a parking space detection result to safely park a vehicle in a parking space is crucial to implementation of the automatic parking function.

This disclosure provides an automatic parking method and apparatus, to improve accuracy of a parking space detection result.

To achieve the foregoing objective, this disclosure uses the following technical solutions.

According to a first aspect, this disclosure provides an automatic parking method. The method includes: determining parking space information of a plurality of candidate parking spaces based on a first image and a second image of an ego vehicle, where the parking space information indicates locations of the parking spaces in a stereo garage, the first image is an environmental image in a first orientation of the ego vehicle, and the second image is a panoramic surround-view image of the ego vehicle; determining a target parking space from the plurality of candidate parking spaces based on the parking space information of the plurality of candidate parking spaces; and controlling the ego vehicle to be parked in the target parking space.

Based on the foregoing technical solution, in a parking scenario of the stereo garage and in a vehicle cruise phase, namely, in a process of searching for a parking space, the parking space information of the plurality of candidate parking spaces is determined based on an environmental image in a specific orientation of the ego vehicle and the panoramic surround-view image of the ego vehicle. The parking space information may indicate the locations of the parking spaces. In other words, the parking spaces are detected based on the environmental image in the specific orientation and the panoramic image. If a parking space is detected in both the environmental image in the first orientation and the panoramic image, it indicates that a probability of existence of the parking space is high. In this way, accuracy of a parking space detection result can be improved. In addition, the panoramic image has a wider field of view, so that a detection probability of a parking space can be improved.

In a possible design, the determining parking space information of a plurality of candidate parking spaces based on a first image and a second image of an ego vehicle includes: determining parking space information of at least one first candidate parking space based on the first image of the ego vehicle, where the first image includes an image of the at least one first candidate parking space; and determining parking space information of at least one second candidate parking space based on the second image of the ego vehicle, where the second image includes an image of the at least one second candidate parking space, and the at least one second candidate parking space includes one or more of the at least one first candidate parking space.

Based on this design, the parking spaces are detected based on the environmental image in the specific orientation and the panoramic image. If a parking space is detected in both the environmental image in the specific orientation and the panoramic image, it indicates that a probability of existence of the parking space is high. In this way, the accuracy of the parking space detection result can be improved. In addition, the panoramic image has a wider field of view, which can improve the detection probability of the parking space.

In a possible design, the parking space information of the at least one first candidate parking space includes at least one of a parking space line, a parking space corner, and a location relationship between parking space corners.

In a possible design, the parking space information of the at least one second candidate parking space includes at least one of an entrance direction of the parking space and vertex coordinates of the parking space.

In a possible design, the determining a target parking space from the plurality of candidate parking spaces based on the parking space information of the plurality of candidate parking spaces includes: determining at least one third candidate parking space based on the parking space information of the at least one first candidate parking space and the parking space information of the at least one second candidate parking space, where the third candidate parking space is a parking space whose confidence level is greater than or equal to a preset confidence level threshold in the at least one second candidate parking space and that belongs to the at least one first candidate parking space, and the confidence level indicates the accuracy of the parking space detection result; and determining the target parking space based on the at least one third candidate parking space.

Based on this design, the target parking space is determined based on the confidence level of the candidate parking space, and the confidence level may reflect accuracy of a parking space detection result. In this way, a candidate parking space whose confidence level meets the preset confidence level threshold, for example, whose confidence level is high, is used as the target parking space, that is, an accurately detected candidate parking space is used as the target parking space. This can further improve the accuracy of the parking space detection result.

In a possible design, the method further includes: capturing a third image of the ego vehicle in a process of controlling the ego vehicle to be parked in the target parking space, where the third image is an environmental image in a third orientation of the ego vehicle, and the third image includes an image of the target parking space; and updating parking space information of the target parking space based on the third image. Based on this design, in the parking scenario of the stereo garage and in a parking phase, that is, in a process of parking the ego vehicle in the target parking space, the parking space information of the target parking space is calibrated by using the third image including the target parking space. This can improve parking accuracy.

In a possible design, the determining parking space information of at least one first candidate parking space based on the first image of the ego vehicle includes: inputting the first image into a first preset model, and outputting the parking space information of the at least one first candidate parking space through the first preset model. Based on this design, the first image is input into the model to recognize the candidate parking space, and in comparison with another feature extraction algorithm, the model is less affected by an environment, light, and the like. This can improve accuracy of a parking space detection result. In addition, in comparison with another feature extraction algorithm, the model avoids excessive manual parameter adjustment and can improve robustness of an overall algorithm.

In a possible design, the determining parking space information of at least one second candidate parking space based on the second image of the ego vehicle includes: inputting the second image into a second preset model, and outputting the parking space information of the at least one second candidate parking space through the second preset model. Based on this design, the panoramic image is input into the model to recognize the candidate parking space, and in comparison with another feature extraction algorithm, the model is less affected by an environment, light, and the like. This can improve accuracy of a parking space detection result. In addition, in comparison with another feature extraction algorithm, the model avoids excessive manual parameter adjustment and can improve robustness of an overall algorithm.

According to a second aspect, this disclosure provides an automatic parking apparatus. The automatic parking apparatus includes a corresponding module or unit for implementing the foregoing method. The module or unit may be implemented by hardware, or may be implemented by software, or may be implemented by hardware by executing corresponding software. In a possible design, the automatic parking apparatus includes a processing unit (or referred to as a processing module). The processing unit is configured to determine parking space information of a plurality of candidate parking spaces based on a first image and a second image of an ego vehicle, where the parking space information indicates locations of the parking spaces in a stereo garage, the first image is an environmental image in a first orientation of the ego vehicle, and the second image is a panoramic surround-view image of the ego vehicle; the processing unit is further configured to determine a target parking space from the plurality of candidate parking spaces based on the parking space information of the plurality of candidate parking spaces; and the processing unit is further configured to control the ego vehicle to be parked in the target parking space.

In a possible design, the processing unit is specifically configured to determine parking space information of at least one first candidate parking space based on the first image of the ego vehicle, where the first image includes an image of the at least one first candidate parking space; and the processing unit is specifically configured to determine parking space information of at least one second candidate parking space based on the second image of the ego vehicle, where the second image includes an image of the at least one second candidate parking space, and the at least one second candidate parking space includes one or more of the at least one first candidate parking space.

In a possible design, the parking space information of the at least one first candidate parking space includes at least one of a parking space line, a parking space corner, and a location relationship between parking space corners.

In a possible design, the parking space information of the at least one second candidate parking space includes at least one of an entrance direction of the parking space and vertex coordinates of the parking space.

In a possible design, the processing unit is specifically configured to determine at least one third candidate parking space based on the parking space information of the at least one first candidate parking space and the parking space information of the at least one second candidate parking space, where the third candidate parking space is a parking space whose confidence level is greater than or equal to a preset confidence level threshold in the at least one second candidate parking space and that belongs to the at least one first candidate parking space, and the confidence level indicates accuracy of a parking space detection result; and the processing unit is specifically configured to determine the target parking space based on the at least one third candidate parking space.

In a possible design, the processing unit is further configured to capture a third image of the ego vehicle in a process of controlling the ego vehicle to be parked in the target parking space, where the third image is an environmental image in a third orientation of the ego vehicle, and the third image includes an image of the target parking space; and the processing unit is further configured to update parking space information of the target parking space based on the third image.

In a possible design, the processing unit is specifically configured to: input the first image into a first preset model, and output the parking space information of the at least one first candidate parking space through the first preset model.

In a possible design, the processing unit is specifically configured to: input the second image into a second preset model, and output the parking space information of the at least one second candidate parking space through the second preset model.

According to a third aspect, this disclosure provides an automatic parking apparatus, including a processor, where the processor is coupled to a memory, and the processor is configured to execute a computer program stored in the memory, for the automatic parking apparatus to perform the method according to the first aspect and any design of the first aspect. Optionally, the memory may be coupled to the processor, or may be independent of the processor.

In a possible design, the automatic parking apparatus further includes a communication interface, and the communication interface may be used by the automatic parking apparatus to communicate with another apparatus. For example, the communication interface may be a transceiver, an input/output interface, an interface circuit, an output circuit, an input circuit, a pin, a related circuit, or the like.

The automatic parking apparatus in the third aspect may be a computing platform in an intelligent driving system, and the computing platform may be an in-vehicle computing platform or a cloud computing platform.

According to a fourth aspect, this disclosure provides a computer-readable storage medium. The computer-readable storage medium includes a computer program or instructions. When the computer program or the instructions are run on an autonomous driving apparatus, the autonomous driving apparatus is enabled to perform the method according to the first aspect and any design of the first aspect.

According to a fifth aspect, this disclosure provides a computer program product. The computer program product includes a computer program or instructions. When the computer program or the instructions are run on a computer, the computer is enabled to perform the method according to the first aspect and any design of the first aspect.

According to a sixth aspect, this disclosure provides a chip system, including at least one processor and at least one interface circuit. The at least one interface circuit is configured to: perform a sending/receiving function, and send instructions to the at least one processor. When the at least one processor executes the instructions, the at least one processor performs the method according to the first aspect and any design of the first aspect.

It should be noted that, for technical effects brought by any design of the second aspect to the sixth aspect, refer to technical effects brought by a corresponding design of the first aspect. Details are not described herein again.

The following describes technical solutions of embodiments in this disclosure with reference to accompanying drawings.

In the descriptions of this disclosure, unless otherwise specified, the character “/” indicates that associated objects are in an “or” relationship. For example, A/B may represent A or B. The term “and/or” in this disclosure merely describes an association relationship between associated objects and indicates that three relationships may exist. For example, A and/or B may represent three cases: Only A exists, both A and B exist, or only B exists, where A and B may be singular or plural.

In addition, in the descriptions of this disclosure, “a plurality of” means two or more than two unless otherwise specified. “At least one of the following items (pieces)” or a similar expression thereof indicates any combination of these items, including a single item (piece) or any combination of a plurality of items (pieces). For example, at least one of a, b, or c may represent: a, b, c, a and b, a and c, b and c, and a and b and c, where a, b, and c may be singular or plural.

In addition, to clearly describe the technical solutions in embodiments of this disclosure, terms such as “first” and “second” are used in embodiments of this disclosure to distinguish between same items or similar items that provide basically same functions or purposes. A person skilled in the art may understand that the terms such as “first” and “second” do not limit a quantity or an execution sequence, and the terms such as “first” and “second” do not indicate a definite difference.

In addition, in embodiments of this disclosure, the word “example” or “for example” indicates giving an example, an illustration, or a description. Any embodiment or design solution described as an “example” or “for example” in embodiments of this disclosure should not be explained as being more preferred or having more advantages than another embodiment or design solution. Exactly, use of the terms such as “example” or “for example” is intended to present a related concept in a specific manner for ease of understanding.

Features, structures, or characteristics in this disclosure may be combined in one or more embodiments in any proper manner. Sequence numbers of processes do not mean execution sequences in embodiments of this disclosure. The execution sequences of the processes should be determined according to functions and internal logic of the processes, and should not be construed as any limitation on the implementation processes of embodiments of this disclosure.

In some scenarios, some optional features in embodiments of this disclosure may be independently implemented without depending on another feature, to resolve a corresponding technical problem and achieve a corresponding effect. Alternatively, in some scenarios, the optional features may be combined with other features based on a requirement.

In this disclosure, unless otherwise specified, for same or similar parts in embodiments, refer to each other. In embodiments of this disclosure, unless otherwise stated or there is a logic conflict, terms and/or descriptions between different embodiments are consistent and may be mutually referenced, and technical features in different embodiments may be combined based on an internal logical relationship thereof, to form a new embodiment. The implementations of this disclosure are not intended to limit the protection scope of this disclosure.

In addition, a network architecture and a service scenario described in embodiments of this disclosure are intended to describe the technical solutions in embodiments of this disclosure more clearly, and do not constitute a limitation on the technical solutions provided in embodiments of this disclosure. A person of ordinary skill in the art may know that: With the evolution of the network architecture and the emergence of a new service scenario, the technical solutions provided in embodiments of this disclosure are also applicable to similar technical problems.

The technical solutions in embodiments of this disclosure may be applied to various automatic parking systems, for example, may be an automatic parking system based on any communication standard like vehicle-to-everything (V2X) communication, device-to-device (D2D) communication, internet of vehicles, or an unmanned driving system.

For example,is a diagram of a system architecture according to an embodiment of this disclosure. As shown in, a systemincludes a control deviceand a vehicle.

The control devicemay be a device that can provide an automatic parking service for the vehicleand that has wireless and/or wired receiving and sending functions, or may be a module, a chip system, a subsystem, or another component disposed inside the device, or may be a device set including a plurality of devices. In embodiments of this disclosure, the device, the device set, the module, the chip, the subsystem, or another component that can provide the automatic parking service is collectively referred to as a control device. The control deviceincludes but is not limited to an automatic parking server, a control module, a terminal device, and the like.

The vehiclemay be a vehicle that supports an automatic parking function. The vehiclemay receive an automatic parking instruction of the control device in a wireless manner, and complete an automatic parking operation according to the instruction; and may receive navigation information from a navigation service provider, and implement autonomous driving based on the navigation information. The vehicleusually has one or more built-in in-vehicle modules, in-vehicle assemblies, in-vehicle components, in-vehicle chips, or in-vehicle units. The vehicle may implement, by using the built-in in-vehicle modules, in-vehicle assemblies, in-vehicle components, in-vehicle chips, or in-vehicle units, an automatic parking method provided in this disclosure. Optionally, the vehicle may further include various devices configured to implement the automatic parking operation, for example, an in-vehicle radar, an in-vehicle infrared imager, an in-vehicle positioning device, an in-vehicle lighting device, and a vehicle control system.

Optionally, the control deviceand the vehiclemay be integrated together, or may be separately disposed.

It may be understood thatis merely a simplified diagram of an example for ease of understanding. During actual application, the foregoing system may further include another device, which is not shown in the figure.

For example, the control devicein this embodiment of this disclosure may be implemented by using different devices. For example, the control devicein this embodiment of this disclosure may be implemented by using a communication device shown in.is a diagram of a hardware structure of the control deviceaccording to an embodiment of this disclosure. The control deviceincludes at least one processor, a communication line, a memory, and at least one communication interface.

The processormay be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to control program execution of the solutions of this disclosure.